© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8437
    Prev
    Next
    INDEX
    Explanations

    the word "hesitate" or words related to an industry

    oai_token-act-pair · gemini-2.0-flash

    professional communications and industry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.82
    '
    -0.81
    :
    -0.63
    $
    -0.62
    ed
    -0.57
    й
    -0.55
    .
    -0.54
    a
    -0.52
    (
    -0.52
    A
    -0.52
    POSITIVE LOGITS
     Мексичка
    1.37
     виправивши
    1.22
     Савезне
    1.22
    IUrlHelper
    1.21
    parsedMessage
    1.16
    MigrationBuilder
    1.13
    فایل‌لار
    1.13
    IntoConstraints
    1.13
     otomatig
    1.12
    Personensuche
    1.11
    Activations Density 0.597%

    No Known Activations